Training in progress, epoch 1

README.md

@@ -14,35 +14,26 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# ai-chat-censor6
+# ai-chat-censor
 
-The primary focus of the model is detecting sexual/minors category of messages.
-Main goal of the model is to detect and prevent illegal use of uncensored chatbots, because of this main focus was detecting "underage" comments.
-Model is trigger happy about this specific tag.
-For example: "Can you roleplay as 16 year old girl" will be tagged as "underage" by this model, meanwhile openai omni-moderation does not flag same message.
-
-
-
-Possible flags are: regular, racist, underage, sexual
+This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1202
+- Accuracy: 0.9879
 
+## Model description
 
-# BEWARE
+More information needed
 
-The model might categorize any talk about race as racism, for example: "Black people suffer so much in America" will be flagged as "racist".
+## Intended uses & limitations
 
+More information needed
 
 ## Training and evaluation data
 
-The model uses variety of datasets, mostly focusing on casual conversation and sexual content.
-The dataset contains around 50k messages.
-Due to a lack of data, underage comments and requests were synthetically generated by uncensored qwen2-72b.
-
-
-This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.0637
-- Accuracy: 0.9903
+More information needed
 
+## Training procedure
 
 ### Training hyperparameters
 
@@ -53,23 +44,22 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 6
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.0471        | 1.0   | 1175 | 0.0729          | 0.9854   |
-| 0.0282        | 2.0   | 2350 | 0.0529          | 0.9900   |
-| 0.0105        | 3.0   | 3525 | 0.0680          | 0.9888   |
-| 0.0079        | 4.0   | 4700 | 0.0558          | 0.9911   |
-| 0.0017        | 5.0   | 5875 | 0.0595          | 0.9902   |
-| 0.0001        | 6.0   | 7050 | 0.0637          | 0.9903   |
+| 0.1279        | 1.0   | 1636 | 0.0890          | 0.9832   |
+| 0.0743        | 2.0   | 3272 | 0.1128          | 0.9861   |
+| 0.0373        | 3.0   | 4908 | 0.1098          | 0.9878   |
+| 0.007         | 4.0   | 6544 | 0.1353          | 0.9886   |
+| 0.0018        | 5.0   | 8180 | 0.1202          | 0.9879   |
 
 
 ### Framework versions
 
-- Transformers 4.44.2
-- Pytorch 2.4.0+cu121
-- Datasets 3.0.0
-- Tokenizers 0.19.1
+- Transformers 4.45.2
+- Pytorch 2.3.1
+- Datasets 3.0.1
+- Tokenizers 0.20.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be391ebd402747377c681f845e350e380b18beba0bd04014dcbf70f98372b207
+oid sha256:0b1e69aaa57a4ef79f298cd928d4412dbd0a3d39416fa48e26c61942d70f8246
 size 267838720

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e50b41dc4b25e4145f04e98320e0954e138e9c7e19324dd73b363c26b9b54a83
+oid sha256:1e7b3b464157ee272958ff03945b69cf348484b701eb667b396853bc4cab6131
 size 5176